TY - GEN
T1 - P-Net
T2 - Conference on Computer Vision and Pattern Recognition Workshop, CVPRW 2003
AU - Shi, Yifan
AU - Bobick, Aaron F.
N1 - Publisher Copyright:
© 2003 IEEE.
PY - 2003
Y1 - 2003
N2 - In this paper, we devise a Propagation Net (P-Net) as a new mechanism for the representation and recognition of multi-stream activity. Most of daily activities can be represented by temporally partial ordered intervals where each interval has not only temporal constraint, i.e., before/after/duration, but also a logical relationship such as a and b both must happen. P-Net associates a node for each interval that is probabilistically triggered function dependent upon the state of its parent nodes. Each node is also associated with an observation distribution function that associates perceptual evidence. This evidence, generated by lower level vision modules, is a positive indicator of the elemental action. Using this architecture, we devise an iterative temporal sequencing algorithm that interprets a multi-dimensional observation sequence of visual evidence as a multi-stream propagation through the P-Net. Simple vision and motion-capture data experiments demonstrate the capabilities of our algorithm.
AB - In this paper, we devise a Propagation Net (P-Net) as a new mechanism for the representation and recognition of multi-stream activity. Most of daily activities can be represented by temporally partial ordered intervals where each interval has not only temporal constraint, i.e., before/after/duration, but also a logical relationship such as a and b both must happen. P-Net associates a node for each interval that is probabilistically triggered function dependent upon the state of its parent nodes. Each node is also associated with an observation distribution function that associates perceptual evidence. This evidence, generated by lower level vision modules, is a positive indicator of the elemental action. Using this architecture, we devise an iterative temporal sequencing algorithm that interprets a multi-dimensional observation sequence of visual evidence as a multi-stream propagation through the P-Net. Simple vision and motion-capture data experiments demonstrate the capabilities of our algorithm.
KW - Activity recognition
KW - Bayesian network
KW - finite
KW - state machine
KW - stochastic state propagation
UR - https://www.scopus.com/pages/publications/41849111569
U2 - 10.1109/CVPRW.2003.10037
DO - 10.1109/CVPRW.2003.10037
M3 - Conference contribution
AN - SCOPUS:41849111569
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 40
EP - 45
BT - 2003 Conference on Computer Vision and Pattern Recognition Workshop, CVPRW 2003
PB - IEEE Computer Society
Y2 - 16 June 2003 through 22 June 2003
ER -